Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.txt

@@ -0,0 +1,20 @@
+accuracy = 0.52
+cls_report =               precision    recall  f1-score   support
+
+         0.0     0.5385    0.1429    0.2258        49
+         1.0     0.5172    0.8824    0.6522        51
+
+    accuracy                         0.5200       100
+   macro avg     0.5279    0.5126    0.4390       100
+weighted avg     0.5276    0.5200    0.4433       100
+
+eval_loss = 0.6898809304604163
+fn = 6
+fp = 42
+macro_f1 = 0.43899018232819076
+mcc = 0.03747366058909428
+tn = 7
+tp = 45
+weighted_f1 = 0.44325385694249647
+weighted_p = 0.5278514588859416
+weighted_r = 0.5126050420168067

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "begin_tag": "<e>", "best_model_dir": "best_model/fr_fr", "cache_dir": "temp/cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 70, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 10, "encoding": null, "end_tag": "</e>", "eval_batch_size": 8, "evaluate_during_training": true, "evaluate_during_training_silent": false, "evaluate_during_training_steps": 20, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": false, "gradient_accumulation_steps": 1, "learning_rate": 1e-05, "local_rank": -1, "logging_steps": 20, "manual_seed": 777, "max_grad_norm": 1.0, "max_seq_length": 120, "model_name": "xlm-roberta-large", "model_type": "xlmroberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "num_train_epochs": 5, "output_dir": "temp/outputs/", "overwrite_output_dir": true, "process_count": 70, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": false, "save_model_every_epoch": false, "save_optimizer_and_scheduler": true, "save_steps": 20, "save_recent_only": true, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 8, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_multiprocessing": false, "wandb_kwargs": {"group": "fr_fr_xlm-roberta-large_CLS_concat", "job_type": "2"}, "wandb_project": "TransWiC-groups", "warmup_ratio": 0.1, "warmup_steps": 57, "weight_decay": 0, "skip_special_tokens": true, "model_class": "ClassificationModel", "labels_list": [0, 1], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "stride": 0.8, "tie_value": 1, "tagging": false, "strategy": "CLS", "special_tags": null, "merge_n": 1, "merge_type": "concat"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6e45a59bfca3560e53ec68c5ee75c5ba614fb979d636c2712aea77db880308
+size 4487768873

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c7dd121c86406650da3cc309927de35bdd7faf8def6b4d72bc356bc37577410
+size 2243936061

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:358c5a102b266abe1e26d94430d927dc1a151702bec6ddede1eb11706168acbe
+size 627

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

test_eval.txt

@@ -0,0 +1,43 @@
+Default classification report:
+              precision    recall  f1-score   support
+
+           F     0.5036    0.1380    0.2166       500
+           T     0.5006    0.8640    0.6339       500
+
+    accuracy                         0.5010      1000
+   macro avg     0.5021    0.5010    0.4253      1000
+weighted avg     0.5021    0.5010    0.4253      1000
+
+
+ADJ
+Accuracy = 0.5489130434782609
+Weighted Recall = 0.5489130434782609
+Weighted Precision = 0.5308763586956522
+Weighted F1 = 0.47553287219318685
+Macro Recall = 0.5128832160324466
+Macro Precision = 0.528125
+Macro F1 = 0.45314570129265586
+ADV
+Accuracy = 0.6333333333333333
+Weighted Recall = 0.6333333333333333
+Weighted Precision = 0.5596153846153846
+Weighted F1 = 0.5823240589198037
+Macro Recall = 0.4841269841269841
+Macro Precision = 0.47115384615384615
+Macro F1 = 0.4599018003273323
+NOUN
+Accuracy = 0.4980544747081712
+Weighted Recall = 0.4980544747081712
+Weighted Precision = 0.4848703726466867
+Weighted F1 = 0.423832547104849
+Macro Recall = 0.4924810322111671
+Macro Precision = 0.48457739260087596
+Macro F1 = 0.4205337947669236
+VERB
+Accuracy = 0.45955882352941174
+Weighted Recall = 0.45955882352941174
+Weighted Precision = 0.5359771380303533
+Weighted F1 = 0.3822956863210408
+Macro Recall = 0.511138682106424
+Macro Precision = 0.5237758945386064
+Macro F1 = 0.40696794862287355

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/home/hh2/.cache/huggingface/transformers/7766c86e10505ed9b39af34e456480399bf06e35b36b8f2b917460a2dbe94e59.a984cf52fc87644bd4a2165f1e07e0ac880272c1e82d648b4674907056912bd7", "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44e7277c7f66328447e9d910bc1272d0d5c4bff2f7bf81bdd0ed7f9ffa94f5c
+size 2811